mcpbeat

Template Engine

claude-office-skills/template-engine

Auto-fill document templates with data - mail merge for any format

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
353
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/claude-office-skills/skills --skill template-engine

The instruction itself

12 sections, as written by the author

Template Engine Skill

Overview

This skill enables template-based document generation - define templates with placeholders, then automatically fill them with data. Works with Word, Excel, PowerPoint, and more.

How to Use

  • Describe what you want to accomplish
  • Provide any required input data or files
  • I'll execute the appropriate operations

Example prompts:

  • "Mail merge for bulk letters/contracts"
  • "Generate personalized reports from data"
  • "Create certificates from templates"
  • "Auto-fill forms with user data"

Domain Knowledge

Template Syntax (Jinja2-based)

{{ variable }}           - Simple substitution
{% for item in list %}   - Loop
{% if condition %}       - Conditional
{{ date | format_date }} - Filter

Word Template Example

from docxtpl import DocxTemplate

# Create template with placeholders:
# Dear {{ name }},
# Thank you for your order #{{ order_id }}...

def fill_template(template_path: str, data: dict, output_path: str):
    doc = DocxTemplate(template_path)
    doc.render(data)
    doc.save(output_path)
    return output_path

# Usage
fill_template(
    "templates/order_confirmation.docx",
    {
        "name": "John Smith",
        "order_id": "ORD-12345",
        "items": [
            {"name": "Product A", "qty": 2, "price": 29.99},
            {"name": "Product B", "qty": 1, "price": 49.99}
        ],
        "total": 109.97
    },
    "output/confirmation_john.docx"
)

Excel Template

from openpyxl import load_workbook
import re

def fill_excel_template(template_path: str, data: dict, output_path: str):
    wb = load_workbook(template_path)
    ws = wb.active
    
    # Find and replace placeholders like {{name}}
    for row in ws.iter_rows():
        for cell in row:
            if cell.value and isinstance(cell.value, str):
                for key, value in data.items():
                    placeholder = "{{" + key + "}}"
                    if placeholder in cell.value:
                        cell.value = cell.value.replace(placeholder, str(value))
    
    wb.save(output_path)
    return output_path

Bulk Generation (Mail Merge)

import csv
from pathlib import Path

def mail_merge(template_path: str, data_csv: str, output_dir: str):
    """Generate documents for each row in CSV."""
    
    Path(output_dir).mkdir(exist_ok=True)
    
    with open(data_csv) as f:
        reader = csv.DictReader(f)
        
        for i, row in enumerate(reader):
            output_path = f"{output_dir}/document_{i+1}.docx"
            fill_template(template_path, row, output_path)
            print(f"Generated: {output_path}")

# Usage with contacts.csv:
# name,email,company
# John,[email protected],Acme
# Jane,[email protected],Corp

mail_merge(
    "templates/welcome_letter.docx",
    "data/contacts.csv",
    "output/letters"
)

Advanced: Conditional Content

from docxtpl import DocxTemplate

# Template with conditionals:
# {% if vip %}
# Thank you for being a VIP member!
# {% else %}
# Thank you for your purchase.
# {% endif %}

doc = DocxTemplate("template.docx")
doc.render({
    "name": "John",
    "vip": True,
    "discount": 20
})
doc.save("output.docx")

Best Practices

  • Use clear placeholder naming ({{client_name}})
  • Validate data before rendering
  • Handle missing data gracefully
  • Keep templates version-controlled

Installation

# Install required dependencies
pip install python-docx openpyxl python-pptx reportlab jinja2

Resources

How to use it

Copy the folder

Take claude-office-skills/template-engine from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip. Without those the skill loads but fails at the first command.